@article{samplingefficientdeepreinforcement,
  title = {Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration},
  author = {Wenhui Huang and Cong Zhang and Jingda Wu and Xiangkun He and Jie Zhang and Chen Lv},
  year = {2022},
  eprint = {2206.09627},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2206.09627v1},
}